# LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs

arXiv: https://arxiv.org/abs/2605.24043 · HTML: https://mlsanity.com/paper/2605.24043/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 28 of 28)

- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [AI Feynman: a Physics-Inspired Method for Symbolic Regression](https://mlsanity.com/paper/1905.11481/) (2019)
- [PDEBENCH: An Extensive Benchmark for Scientific Machine Learning](https://mlsanity.com/paper/2210.07182/) (2022)
- [Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients](https://mlsanity.com/paper/1912.04871/) (2019)
- [LLM-SR: Scientific Equation Discovery via Programming with Large Language Models](https://mlsanity.com/paper/2404.18400/) (2024)
- [The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4](https://mlsanity.com/paper/2311.07361/) (2023)
- [Symbolic Regression with a Learned Concept Library](https://mlsanity.com/paper/2409.09359/) (2024)
- [Hypothesis Generation with Large Language Models](https://mlsanity.com/paper/2404.04326/) (2024)
- [LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models](https://mlsanity.com/paper/2504.10415/) (2025)
- [ODEFormer: Symbolic Regression of Dynamical Systems with Transformers](https://mlsanity.com/paper/2310.05573/) (2023)
- [Efficient Evolutionary Search Over Chemical Space with Large Language Models](https://mlsanity.com/paper/2406.16976/) (2024)
- [AI4Research: A Survey of Artificial Intelligence for Scientific Research](https://mlsanity.com/paper/2507.01903/) (2025)
- [Active learning machine learns to create new quantum experiments](https://mlsanity.com/paper/1706.00868/) (2017)
- [Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challenges](https://mlsanity.com/paper/2412.11427/) (2024)
- [NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents](https://mlsanity.com/paper/2510.07172/) (2025)
- [Data-driven Discovery with Large Generative Models](https://mlsanity.com/paper/2402.13610/) (2024)
- [AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise](https://mlsanity.com/paper/2507.00310/) (2025)
- [Olympus: a benchmarking framework for noisy optimization and experiment planning](https://mlsanity.com/paper/2010.04153/) (2020)
- [High-Dimensional Materials and Process Optimization using Data-driven Experimental Design with Well-Calibrated Uncertainty Estimates](https://mlsanity.com/paper/1704.07423/) (2017)
- [LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discovery](https://mlsanity.com/paper/2510.22503/) (2025)
- [ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein-Specific Molecular Generation](https://mlsanity.com/paper/2309.05853/) (2023)
- [MatLLMSearch: Crystal Structure Discovery with Evolution-Guided Large Language Models](https://mlsanity.com/paper/2502.20933/) (2025)
- [Practical optimal experiment design with probabilistic programs](https://mlsanity.com/paper/1608.05046/) (2016)
- [AutoSciLab: A Self-Driving Laboratory For Interpretable Scientific Discovery](https://mlsanity.com/paper/2412.12347/) (2024)
- [Generating Literature-Driven Scientific Theories at Scale](https://mlsanity.com/paper/2601.16282/) (2026)
- [Active Symbolic Discovery of Ordinary Differential Equations via Phase Portrait Sketching](https://mlsanity.com/paper/2409.01416/) (2024)
- [Active learning for efficient discovery of optimal gene combinations in the combinatorial perturbation space](https://mlsanity.com/paper/2411.12010/) (2024)
- [SURFACEBENCH: A Geometry-Aware Benchmark for Symbolic Surface Discovery](https://mlsanity.com/paper/2511.10833/) (2025)

## Built on by (most cited first, 12 of 12)

- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Search](https://mlsanity.com/paper/2606.25039/) (2026)
- [Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models](https://mlsanity.com/paper/2608.09696/) (2026)
- [EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation](https://mlsanity.com/paper/2609.01526/) (2026)
- [EurekaBench: Measuring Agentic Ability to Discover New Scientific Insights](https://mlsanity.com/paper/2610.00492/) (2026)
- [Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents](https://mlsanity.com/paper/2610.02525/) (2026)
- [Learning to Outgrow a Theory: Experimental Discovery Beyond the Initial Hypothesis Space](https://mlsanity.com/paper/2610.07627/) (2026)
- [Kernel Autoresearch for Open-Ended Model Discovery](https://mlsanity.com/paper/2610.10394/) (2026)
- [LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models](https://mlsanity.com/paper/2610.11253/) (2026)
- [EvoBelief: Falsifiable World Models for Self-Improving LLM Agents](https://mlsanity.com/paper/2610.12789/) (2026)
- [Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery](https://mlsanity.com/paper/2610.18449/) (2026)
- [Beyond Equation Search: Conjecture-Guided Discovery with SCOPE and ClosureBench](https://mlsanity.com/paper/2610.18938/) (2026)

## Abstract (arXiv)

Scientific discovery is a closed-loop process in which hypotheses guide data acquisition and observations refine the hypothesis space. Yet most approaches reduce discovery to supervised learning over fixed datasets, where limited observations can support multiple plausible mechanisms that fit locally but fail to generalize. Thus, the key challenge is selecting informative observations to resolve uncertainty, shifting the focus from static inference to adaptive data acquisition. To address this, we propose LLM-AutoSciLab, a closed-loop framework that couples hypothesis generation with hypothesis-conditioned experiment selection and mechanism refinement. Rather than fitting models to passively collected data, LLM-AutoSciLab iteratively proposes plausible hypotheses, selects informative experiments to distinguish or refine them, and updates its state using the resulting evidence. To evaluate dynamic, closed-loop scientific discovery with active data acquisition, we introduce ActiveSciBench, comprising two datasets: ActiveSciBench-Chem with 57 enzyme-kinetics tasks and ActiveSciBench-GRN with 45 gene-regulatory-network tasks. These datasets model discovery as a budget-constrained process requiring adaptive experiment design, variable selection, and recovery of true mechanisms. Across NewtonBench, ActiveSciBench-Chem, and ActiveSciBench-GRN, LLM-AutoSciLab outperforms prior methods, achieving 67.6% and 35.1% symbolic accuracy on NewtonBench and ActiveSciBench-Chem, respectively, and 31.1% exact graph recovery on ActiveSciBench-GRN. Moreover, hypothesis-guided experimentation is 2-5x more sample-efficient than the strongest competing baselines. Code and data are available at: https://github.com/scientific-discovery/LLM-AutoSciLab